ICP Intelligence MCP
Server provides 9 read-only, rule-based B2B ICP intelligence tools for customer profiling, market sizing, buyer mapping, targeting, and account prioritization.
Analyze best-customer patterns and contract-value ranges with
icp_deep_dive.Build lead-scoring templates, weights, scorecards, and tier bands with
icp_scoring_model.Map buying groups, stakeholder roles, influence, concerns, and discovery questions with
buyer_group_analyzer.Calculate bottom-up TAM/SAM/SOM with shown assumptions for investor summaries with
tam_sam_som_calculator.Generate lookalike targeting criteria, platform queries, trigger signals, and keywords with
lookalike_signal_generator.Rank accounts by weighted fit, intent, relationship, and timing with
account_prioritization.Compare current customers against an ideal profile and identify metric gaps and actions with
icp_gap_analysis.Generate candidate ICP changes from wins, losses, and market shifts with
icp_evolution_tracker.Synthesize structured customer interview notes into pain points, triggers, quotes, and discovery questions with
icp_interview_synthesizer.Use it hosted with no sign-in at
https://icp-intelligence.gtmhelix.com/mcp, or locally via the older npm stdio package.The tools work only from supplied inputs, perform no company/contact lookups, store no inputs or outputs, and record only hosted usage metadata.
Generates Google Ads targeting criteria and search queries based on champion titles, ICP firmographics, technographics, and buying triggers via the lookalike signal generator tool.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ICP Intelligence MCP Define our ideal customer profile based on top 10 customers."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ICP Intelligence MCP v1.2.28
By Helix GTM Consulting (https://gtmhelix.com), built by Shashwat Ghosh, Co-Founder and Fractional CMO.
Deep ICP Analysis with Pattern Detection: 9 tools for ideal customer profiling, market sizing, buyer mapping, and account prioritization.
Use it hosted (no install)
Add https://icp-intelligence.gtmhelix.com/mcp to Claude or ChatGPT as a custom connector, or to Codex or Gemini CLI as an MCP server. It needs no sign-in and always runs the newest version (1.2.28). The same tools run as a free web app with a form per tool at https://icp-intelligence.gtmhelix.com/, and the setup steps are at https://icp-intelligence.gtmhelix.com/connect/.
The npm package below is an older version (1.0.0 on npm on 27 September 2026) until the next npm release. Use it only if you need a local stdio server.
Related MCP server: Sales Prospector
Quick Start
# Run directly with npx
npx -y @shashwatgtmalpha/icp-intelligence-mcpClaude Desktop Configuration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"icp-intelligence-mcp": {
"command": "npx",
"args": ["-y", "@shashwatgtmalpha/icp-intelligence-mcp"]
}
}
}Tools and inputs
Tool names and input formats were checked against tools/list of icp-intelligence-mcp 1.2.28 on 17 November 2026. Query tools/list for current descriptions.
# | Tool | Title | What it does |
1 |
| ICP Deep Dive | Helps you decide which customers to go after next. You give your best customers, as a list (industry, size, contract value, sales cycle, tech stack, buying trigger, champion title) or in your own words. You get the patterns they share, with ties named as ties, the budget shown as the contract value range seen in your customers, recommendations, and sector notes when your inputs name a supported sector. It works only from what you give and looks nothing up. |
2 |
| ICP Scoring Model | Helps you decide which leads are worth a seller's time. You give the criteria that matter, how important each one is and, if you know it, what goes with success. You get a lead scoring template: example point weights set by importance level, example points for each value you list, a scorecard and tier bands to adjust, with sector notes when your inputs name a supported sector. Your success pattern is matched to your criteria; it does not set the weights. |
3 |
| Buyer Group Analyzer | Helps you decide who else must agree before a deal can close. You give what you sell, the deal size, the company size, your champion and any stakeholders you know. You get a buying group map with your stakeholders placed by their titles (economic buyer, technical evaluator, reviewers, users), each role's concern and message prompts, an influence map and discovery questions, with sector roles and questions when your inputs name a supported sector. Roles from titles are hypotheses to confirm. |
4 |
| TAM SAM SOM Calculator | Helps you decide how big your market is, counted bottom up. You give how many companies could buy and your annual contract value in dollars, plus your ICP match rate and year 1 share if you have them. You get TAM, SAM and SOM with the arithmetic and assumptions shown and a summary for an investor deck. It is a calculator, not a data source: a rate you leave out is filled with a labelled example, and sector notes are added when your inputs name a supported sector. |
5 |
| Lookalike Signal Generator | Helps you decide how to find more accounts like your best ones. You give your ICP's company profile, technologies, champion titles and buying triggers, and optionally what you sell and the platforms you use. You get targeting criteria and search queries for each platform, one signal for each trigger, and search keywords from what you sell and the sector. It writes criteria, not data: it finds no companies or contacts. |
6 |
| Account Prioritization | Helps you decide which accounts to work first. You give your accounts with fit, intent and relationship scores from 0 to 100 and a timing, plus optional weights. You get a ranked list from a weighted score, with a tier for each account, the points its timing earned and the factor that added the most points. |
7 |
| ICP Gap Analysis | Helps you decide whether you are selling to the customers you meant to. You give your current customer base, your ideal customer profile and, if you have them, current and target metrics. You get what the ideal profile has that the current base lacks, metric gaps from your own figures, causes to check and actions that fit your business model, with sector notes when your inputs name a supported sector. |
8 |
| ICP Evolution Tracker | Helps you decide whether your ICP should change after recent wins and losses. You give your current ICP, recent wins, recent losses and market changes. You get a candidate change for each (an addition to test, a disqualifier to test, an implication to check), a draft of the updated ICP, the roles your ICP does not name, the loss reasons to tag and what to pull from your CRM. It does not compute win rates; check each candidate against your CRM. |
9 |
| ICP Interview Synthesizer | Helps you decide what your customer interviews mean for your ICP. You give structured notes, one per interview: the customer, the role, pain points, buying triggers, value realized and key quotes. You get the pain points, objections, buying triggers, value realized and champion roles across the interviews, quotes kept word for word, discovery questions and sector notes. It does not take full transcripts; give only the points and quotes you want analyzed. |
Inputs of each tool
1. ICP Deep Dive (icp_deep_dive)
Input | Required | Type | Description |
| No | array of object | List of customer objects with available attributes |
| No | string | Alternative: Describe your best customers in text format |
| No | string | What type of product you sell |
| No | string | Optional: your company or product name, so the answer can name it |
| No | string | Optional: how you charge (software subscription, services, connectivity, per transaction, marketplace, hardware plus software, or investment management). Read from your other inputs when left out (allowed: |
2. ICP Scoring Model (icp_scoring_model)
Input | Required | Type | Description |
| No | array of object | Criteria for scoring with importance levels |
| No | string | What correlates with success? (e.g., "deals with VP Sales champion close 2x faster") |
| No | string | What type of product you sell |
| No | string | Optional: your company or product name, so the answer can name it |
3. Buyer Group Analyzer (buyer_group_analyzer)
Input | Required | Type | Description |
| Yes | string | What you sell |
| No | string | ACV range (e.g., "$50K-100K") |
| No | string | Company size (e.g., "500-1000 employees") |
| No | array of string | Roles you know are involved |
| No | string | Your typical champion role |
| No | string | Optional: your company or product name, so the answer can name it |
| No | string | Optional: how you charge (software subscription, services, connectivity, per transaction, marketplace, hardware plus software, or investment management). Read from your other inputs when left out (allowed: |
4. TAM SAM SOM Calculator (tam_sam_som_calculator)
Input | Required | Type | Description |
| Yes | number (0 or more) | Estimated total companies that could buy (from LinkedIn, industry reports) |
| Yes | number (more than 0) | Your average ACV in dollars |
| No | number (0 or more) | Percentage of those companies that match your ICP, from 0 to 100. Left out, 30 is used and marked as an example |
| No | number (0 or more) | Realistic Year 1 market share percentage, from 0 to 100 (typically 1-5%). Left out, 3 is used and marked as an example |
| No | string | Where you got your numbers (for documentation) |
| No | string | Name of the market segment |
| No | string | Optional: what you sell (for example "spend management software"), used for sector notes. The arithmetic does not use it |
| No | string | Optional: your company or product name, so the answer can name it |
5. Lookalike Signal Generator (lookalike_signal_generator)
Input | Required | Type | Description |
| Yes | array of string | Job titles of your champions |
| No | object | Firmographic criteria |
| No | array of string | Technologies your ICP typically uses |
| No | array of string | Events that trigger buying |
| No | array of string | Optional: the sections to include (linkedin, google_ads, 6sense, zoominfo). Left out, every section is included |
| No | string | Optional: what you sell (for example "spend management software"), used for search keywords and sector notes |
| No | string | Optional: your company or product name, so the answer can name it |
6. Account Prioritization (account_prioritization)
Input | Required | Type | Description |
| No | array of object | List of accounts to prioritize. Each account: name, fit_score (0 to 100), intent_signals (0 to 100), relationship (0 to 100), timing (now, soon, later or unknown) |
| No | object | Optional custom weights in percent for fit, intent, relationship and timing. A missing weight uses its default (40, 30, 15, 15); the tool does not check that the weights sum to 100 |
| No | string | Optional: what you sell (for example "spend management software"), used for sector notes. The arithmetic does not use it |
| No | string | Optional: your company or product name, so the answer can name it |
7. ICP Gap Analysis (icp_gap_analysis)
Input | Required | Type | Description |
| Yes | string | Description of your current customer base |
| Yes | string | Description of your ideal customer profile |
| No | object | Current performance metrics |
| No | object | Target performance metrics |
| No | string | Optional: what you sell, used for sector notes |
| No | string | Optional: your company or product name, so the answer can name it |
| No | string | Optional: how you charge (software subscription, services, connectivity, per transaction, marketplace, hardware plus software, or investment management). Read from your other inputs when left out (allowed: |
8. ICP Evolution Tracker (icp_evolution_tracker)
Input | Required | Type | Description |
| Yes | string | Your current ICP definition |
| No | string | Description of recent successful customers |
| No | string | Description of recent lost deals |
| No | string | Recent market or competitive changes |
| No | string | Time period you are reviewing, in your own words (for example "last quarter") |
| No | string | Optional: what you sell, used for sector notes |
| No | string | Optional: your company or product name, so the answer can name it |
9. ICP Interview Synthesizer (icp_interview_synthesizer)
Input | Required | Type | Description |
| No | array of object | Structured interview notes: one object per interview with the customer (company or segment), the role of the person interviewed and the points and quotes to analyze |
| No | string | Optional: what you sell, used for sector notes |
| No | string | Optional: your company or product name, so the answer can name it |
Who Is This For?
Primary Users
Role | Key Tools | Use Cases |
Founders/CEOs |
| Market sizing, customer definition |
CMOs/VPs Marketing |
| ICP health monitoring |
Product Marketing |
| Buying committee, VOC |
Demand Gen |
| Targeting, ABM |
Sales Ops/RevOps |
| Lead scoring, account tiering |
SDRs/BDRs |
| Account qualification |
Job-to-Tool Mapping
Job To Be Done | Recommended Tool |
"I need to define our ideal customer profile" |
|
"I need to create a lead scoring model" |
|
"I need to compare our actual vs ideal customers" |
|
"I need to track how our ICP is changing" |
|
"I need to synthesize customer interview insights" |
|
"I need to map the buying committee" |
|
"I need to calculate our TAM/SAM/SOM" |
|
"I need targeting criteria for ad platforms" |
|
"I need to prioritize our target accounts" |
|
Related MCPs
MCP | Focus | Tools | Link |
CRAFT GTM | GTM strategy | 8 | |
CRAFT Content | Content creation | 8 | |
IMPACT | B2B positioning | 8 | |
Revenue Enablement | Sales execution | 12 |
ICP Intelligence Philosophy
This MCP is built on the principle that ICP is dynamic, not static. The best B2B companies continuously refine their ICP based on:
Win/loss patterns
Customer success metrics
Market evolution
Product capabilities
Key Principles:
Data-driven: Ground ICP in actual customer data
Multi-dimensional: Beyond firmographics to behavior
Actionable: Translate ICP to targeting criteria
Iterative: Regular refinement cycles
Author
Shashwat Ghosh, Co-Founder and Fractional CMO, Helix GTM Consulting, with 24+ years in B2B and 10+ years of fractional experience
License
MIT License: see LICENSE for details.
Part of the Helix GTM Consulting MCP suite: rule-based B2B go-to-market tools (no AI model runs inside them)
Hosted connector (Streamable HTTP)
The same tools are also available as a hosted MCP server, so they work in Claude on the web, desktop and mobile without installing anything.
Server URL:
https://icp-intelligence.gtmhelix.com/mcpTransport: Streamable HTTP (stateless, JSON responses). Authentication: none.
Setup guide: https://icp-intelligence.gtmhelix.com/connect/
In Claude: Customize, then Connectors, then Add custom connector, and paste the server URL.
In Claude Code:
claude mcp add --transport http icp-intelligence https://icp-intelligence.gtmhelix.com/mcp
The npm package (stdio) and the hosted server run the same createServer() code in src/index.ts.
The tool reference on the docs page (https://icp-intelligence.gtmhelix.com/docs/) is generated from the code. Where it differs from the parameter tables earlier in this README, the docs page is correct.
Privacy Policy
Full policy: https://icp-intelligence.gtmhelix.com/privacy/ (also in PRIVACY.md).
Data collection: the hosted server receives only the tool name and the inputs of each tool call. The npm package runs on your computer and sends nothing to us.
Use and storage: inputs are used only to build that call's reply. Inputs and answers are not stored: no database, no files, no cache, no logging of inputs or outputs by our code. Each call adds one anonymous usage record (date and time, site and tool name, app kind, web form or assistant); see the privacy page.
Third-party sharing: none by us. Netlify hosts the server and processes requests under its own policy (https://www.netlify.com/privacy/). Fonts are served from this site, so loading a page contacts no one else.
Retention: we keep no tool inputs or outputs. Netlify keeps its own platform logs under its policy.
Contact: shashwat@gtmhelix.com
Available Tools
9 toolsaccount_prioritizationAccount PrioritizationARead-onlyInspect
Helps you decide which accounts to work first. You give your accounts with fit, intent and relationship scores from 0 to 100 and a timing, plus optional weights. You get a ranked list from a weighted score, with a tier for each account, the points its timing earned and the factor that added the most points. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Without accounts, it returns the scoring framework and an example input. Missing account scores default to 50. Invalid ranges or all-zero weights return an error. Use this instead of icp_scoring_model when you have accounts and numeric scores ready to rank.
Inputs: company, accounts, product_category, prioritization_weights.
buyer_group_analyzerBuyer Group AnalyzerARead-onlyInspect
Helps you decide who else must agree before a deal can close. You give what you sell, the deal size, the company size, your champion and any stakeholders you know. You get a buying group map with your stakeholders placed by their titles (economic buyer, technical evaluator, reviewers, users), each role's concern and message prompts, an influence map and discovery questions, with sector roles and questions when your inputs name a supported sector. Roles from titles are hypotheses to confirm. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of impact_identify_champions when you need a deal buying-group map covering budget, technical and review roles.
Inputs: product_category (required), company, deal_size, business_model, +4 more.
icp_deep_diveICP Deep DiveARead-onlyInspect
Helps you decide which customers to go after next. You give your best customers, as a list (industry, size, contract value, sales cycle, tech stack, buying trigger, champion title) or in your own words. You get the patterns they share, with ties named as ties, the budget shown as the contract value range seen in your customers, recommendations, and sector notes when your inputs name a supported sector. It works only from what you give and looks nothing up. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Without customers or customer_descriptions, it returns a request for customer data with example input formats. Invalid typed values return a correction error. Use this instead of icp_gap_analysis when you need patterns in supplied customers before comparing them with an ideal profile.
Inputs: company, customers, business_model, product_category, +1 more.
icp_evolution_trackerICP Evolution TrackerARead-onlyInspect
Helps you decide whether your ICP should change after recent wins and losses. You give your current ICP, recent wins, recent losses and market changes. You get a candidate change for each (an addition to test, a disqualifier to test, an implication to check), a draft of the updated ICP, the roles your ICP does not name, the loss reasons to tag and what to pull from your CRM. It does not compute win rates; check each candidate against your CRM. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of icp_gap_analysis when you need candidate ICP changes from recent wins, losses and market shifts.
Inputs: current_icp (required), company, recent_wins, time_period, +3 more.
icp_gap_analysisICP Gap AnalysisARead-onlyInspect
Helps you decide whether you are selling to the customers you meant to. You give your current customer base, your ideal customer profile and, if you have them, current and target metrics. You get what the ideal profile has that the current base lacks, metric gaps from your own figures, causes to check and actions that fit your business model, with sector notes when your inputs name a supported sector. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of icp_evolution_tracker when you need to compare the current customer base with a stated ideal profile.
Inputs: ideal_icp (required), current_customers (required), company, business_model, +3 more.
icp_interview_synthesizerICP Interview SynthesizerARead-onlyInspect
Helps you decide what your customer interviews mean for your ICP. You give structured notes, one per interview: the customer, the role, pain points, buying triggers, value realized and key quotes. You get the pain points, objections, buying triggers, value realized and champion roles across the interviews, quotes kept word for word, discovery questions and sector notes. It does not take full transcripts; give only the points and quotes you want analyzed. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Without interview_notes, it returns the structured-notes format to supply. Invalid typed values return a correction error. Use this instead of customer_interview_kit when you already have structured interview notes to analyze.
Inputs: company, interview_notes, product_category.
icp_scoring_modelICP Scoring ModelARead-onlyInspect
Helps you decide which leads are worth a seller's time. You give the criteria that matter, how important each one is and, if you know it, what goes with success. You get a lead scoring template: example point weights set by importance level, example points for each value you list, a scorecard and tier bands to adjust, with sector notes when your inputs name a supported sector. Your success pattern is matched to your criteria; it does not set the weights. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Without scoring_criteria, it returns a labelled example model. Invalid values return a correction error. Incomplete or failed held_back_test evidence holds the scoring decision. Use this instead of account_prioritization when you need a reusable scoring template before ranking named accounts. Ask for held-back test counts and the pre-agreed stop rule when a model has been tested.
Inputs: company, held_back_test, product_category, scoring_criteria, +2 more.
lookalike_signal_generatorLookalike Signal GeneratorARead-onlyInspect
Helps you decide how to find more accounts like your best ones. You give your ICP's company profile, technologies, champion titles and buying triggers, and optionally what you sell and the platforms you use. You get targeting criteria and search queries for each platform, one signal for each trigger, and search keywords from what you sell and the sector. It writes criteria, not data: it finds no companies or contacts. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of icp_deep_dive when you already have an ICP and need search criteria and trigger signals.
Inputs: champion_titles (required), company, platforms, buying_triggers, +3 more.
tam_sam_som_calculatorTAM SAM SOM CalculatorARead-onlyInspect
Helps you decide how big your market is, counted bottom up. You give how many companies could buy and your annual contract value in dollars, plus your ICP match rate and year 1 share if you have them. You get TAM, SAM and SOM with the arithmetic and assumptions shown and a summary for an investor deck. It is a calculator, not a data source: a rate you leave out is filled with a labelled example, and sector notes are added when your inputs name a supported sector. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of impact_anchor_market when you have a chosen market and need bottom-up market arithmetic.
Inputs: average_contract_value (required), total_potential_companies (required), company, data_sources, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Each tool targets a distinct analytical artifact (customer patterns, scoring template, buying group map, market sizing, targeting criteria, account ranking, gap analysis, ICP evolution, interview synthesis), and most descriptions include explicit 'use this instead of X' routing guidance. The remaining overlap is real but bounded: icp_deep_dive/icp_gap_analysis/icp_evolution_tracker all reason over customers and ICP, and icp_scoring_model vs account_prioritization both produce scoring artifacts, so an agent must read the routing hints carefully to choose correctly.
All names are snake_case, which is good, but the convention is mixed: some are noun-phrase artifacts (icp_scoring_model, account_prioritization, tam_sam_som_calculator) while others are action phrases (icp_deep_dive, icp_gap_analysis), and only some end in an agent suffix (-analyzer, -calculator, -generator, -synthesizer). The 'icp_' prefix appears on five of nine tools, so grouping is inferable but not predictable.
Nine tools is well within a healthy range and each one maps to a distinct step in the ICP/GTM strategy workflow, from discovery through sizing, targeting, prioritization, and ICP refresh. No tool appears redundant or filler.
The surface covers the core ICP lifecycle well: customer pattern mining, scoring, buying-group mapping, market sizing, lookalike targeting, account ranking, gap analysis, evolution, and interview synthesis. Minor gaps exist around competitive/positioning or messaging output and any persistence/export of results, but the tools are explicitly stateless by design, so agents can work around these.
Maintenance
Related MCP Connectors
Find the companies and people that fit your ICP, with verified emails, across 87M+ companies.
Sales intelligence for B2B SMEs — lead scoring, ICP fit, CRM enrichment & writeback.
AI account intelligence for B2B sales: account briefs, buying signals and contacts.
AI sales — prospect discovery, ICP scoring, outreach generation.
Related MCP Servers
- AlicenseAqualityBmaintenanceRevenue intelligence for complex B2B growth. Your agent builds the assets technical founders sell with, and prepares them for real buyer conversations.34398 npm2MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to automate sales prospecting by finding contacts by role and industry, enriching data with emails and tech stacks, scoring against ideal customer profiles, and generating personalized outreach sequences. Streamlines lead generation and sales engagement workflows through integrated research and sequence generation tools.MIT
- AlicenseAqualityBmaintenanceDeal Strategy & Sales Enablement Engine - 12 tools for sales execution, deal management, and revenue acceleration.12287 npm1MIT
- AlicenseAqualityBmaintenanceAn MCP server providing 8 content creation tools for case studies, newsletters, webinars, and more, based on the CRAFT Framework.9265 npmMIT